grant-compliance-checking
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is purely instructional and provides a framework for reviewing project compliance with research grant requirements from agencies like NSF, NIH, and the EU.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read external project documents (e.g.,
/grant/,/proposal/,specification*.md). This represents a standard data ingestion surface, but the skill does not possess dangerous capabilities like network exfiltration or shell execution that would make this surface critical.
Audit Metadata